© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8635
    Prev
    Next
    INDEX
    Explanations

    white-collar crimes and murder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Гар
    0.57
    ুখে
    0.53
    </div>
    0.52
     начале
    0.51
    <table>
    0.49
     Игра
    0.49
    garia
    0.48
     Ninh
    0.47
    zął
    0.46
    </td>
    0.45
    POSITIVE LOGITS
     ergibt
    0.50
     ripet
    0.48
     comparte
    0.48
     diagn
    0.47
     physi
    0.46
     descu
    0.46
     aspett
    0.45
     blad
    0.45
     make
    0.45
    لي
    0.45
    Activations Density 0.019%

    No Known Activations